Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4430 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6864. Min Act: -0.0000

Data Index: 1680025 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7048. Min Act: -0.0000

Data Index: 1003763 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5446. Min Act: -0.0000

Data Index: 639546 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3765. Min Act: -0.0000

Data Index: 1658310 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.8083. Min Act: -0.0000

Data Index: 87966 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3912. Min Act: -0.0000

Data Index: 1108962 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2751. Min Act: -0.0000

Data Index: 470360 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2314. Min Act: -0.0000

Data Index: 1207054 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3597. Min Act: -0.0000

Data Index: 49758 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3085. Min Act: -0.0000

Data Index: 1803138 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.0614. Min Act: -0.0000

Data Index: 350538 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5325. Min Act: -0.0000

Data Index: 1831173 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3421. Min Act: -0.0000

Data Index: 1881593 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3864. Min Act: -0.0000

Data Index: 408482 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.1687. Min Act: -0.0000

Data Index: 1535000 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2152. Min Act: -0.0000

Data Index: 59118 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.0449. Min Act: -0.0000

Data Index: 1346759 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.1771. Min Act: -0.0000

Data Index: 730771 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4100. Min Act: -0.0000

Data Index: 1724695 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2363. Min Act: -0.0000

Data Index: 578630 (The Pile)

Max Activating Token Index: 278